Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models
This work addresses the challenge of complex cost structures in domains like healthcare, offering a practical solution for cost-sensitive model deployment, though it is incremental in its application to specific risk prediction problems.
The authors tackled the problem of trading off deployment cost versus prediction accuracy in predictive models, particularly for healthcare risk prediction, by proposing a novel framework using boolean circuits to design cost-sensitive structured regularizers, resulting in models that achieve an excellent accuracy-cost tradeoff for sepsis risk prediction in intensive care units.
Predictive models are finding an increasing number of applications in many industries. As a result, a practical means for trading-off the cost of deploying a model versus its effectiveness is needed. Our work is motivated by risk prediction problems in healthcare. Cost-structures in domains such as healthcare are quite complex, posing a significant challenge to existing approaches. We propose a novel framework for designing cost-sensitive structured regularizers that is suitable for problems with complex cost dependencies. We draw upon a surprising connection to boolean circuits. In particular, we represent the problem costs as a multi-layer boolean circuit, and then use properties of boolean circuits to define an extended feature vector and a group regularizer that exactly captures the underlying cost structure. The resulting regularizer may then be combined with a fidelity function to perform model prediction, for example. For the challenging real-world application of risk prediction for sepsis in intensive care units, the use of our regularizer leads to models that are in harmony with the underlying cost structure and thus provide an excellent prediction accuracy versus cost tradeoff.